ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Trinity Large Thinking vs Ornith 1.5 122B vs Mercury Edit 2

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Arcee AI

    Trinity Large Thinking

    Released Apr 1, 2026Beta

    55/100
    • ECI—
    • Price$0.25 / $0.80
    • Context524K
  2. DeepReinforce

    Ornith 1.5 122B

    Released Oct 20, 2026New

    63/100
    • ECI—
    • Price$0.16 / $0.64
    • Context262K
  3. Inception

    Mercury Edit 2

    Released Mar 30, 2026

    36/100
    • ECI—
    • Price$0.25 / $0.75
    • Context32K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Ornith 1.5 122B 63/100, Trinity Large Thinking 55/100, Mercury Edit 2 36/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceOrnith 1.5 122BOrnith 1.5 122B $0.28 · Mercury Edit 2 $0.375 · Trinity Large Thinking $0.388 per 1M tokens (3:1 blend)
  • Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · Ornith 1.5 122B 262,144 · Mercury Edit 2 32,000 tokens
  • Widest inputsOrnith 1.5 122BTrinity Large Thinking: Text · Ornith 1.5 122B: Text, Images · Mercury Edit 2: Text
  • Self-hostingTrinity Large Thinking and Ornith 1.5 122BPublishes downloadable weights (OpenMDW-1.1 and MIT)
How the score is built
MeasureWeightTrinity Large ThinkingOrnith 1.5 122BMercury Edit 2
Price50%667367
Inputs & features30%35600
Context window20%544310
Specs & price only100%55/10063/10036/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Trinity Large Thinking vs Ornith 1.5 122B vs Mercury Edit 2 specifications side by side
SpecificationTrinity Large ThinkingArcee AIOrnith 1.5 122BDeepReinforceMercury Edit 2Inception
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.25$0.16 (best)$0.25
Output$0.80$0.64 (best)$0.75
Cached input$0.06—$0.025 (best)
Blended (3:1)$0.388$0.28 (best)$0.375
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Arcee APIMedian of 1 providersOfficial Inception API
Limits
Context window524,288 tokens (best)262,144 tokens32,000 tokens
Max output262,144 tokens (best)32,768 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenMDW-1.1OpenMITProprietary
API model IDtrinity-large-thinking—mercury-edit-2
API providers2 (best)11
ReleasedApr 1, 2026Oct 20, 2026Mar 30, 2026
Knowledge cutoff———
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Trinity Large Thinking$4.10
  • Ornith 1.5 122B$2.88
  • Mercury Edit 2$4.00
04 — Questions

Which should you choose?

Which is better: Trinity Large Thinking, Ornith 1.5 122B or Mercury Edit 2?

There is not enough shared capability evidence to name an overall winner. The scores (Ornith 1.5 122B 63/100, Trinity Large Thinking 55/100, Mercury Edit 2 36/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Trinity Large Thinking, Ornith 1.5 122B or Mercury Edit 2?

Ornith 1.5 122B is cheaper at $0.16 input / $0.64 output per million tokens (median across 1 API provider). Mercury Edit 2 costs $0.25 input / $0.75 output per million tokens (official Inception API price); Trinity Large Thinking costs $0.25 input / $0.80 output per million tokens (official Arcee API price). At a typical mix of three input tokens to one output token, that is $0.28 per million tokens for Ornith 1.5 122B versus $0.375 for Mercury Edit 2 (1.3× as much) and $0.388 for Trinity Large Thinking (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Trinity Large Thinking has not been scored yet, Ornith 1.5 122B has not been scored yet and Mercury Edit 2 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Trinity Large Thinking, Ornith 1.5 122B and Mercury Edit 2 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Mercury Edit 2 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Trinity Large Thinking has the largest context window at 524,288 tokens, against 262,144 for Ornith 1.5 122B and 32,000 for Mercury Edit 2. Maximum output per response: Trinity Large Thinking up to 262,144, Ornith 1.5 122B up to 32,768, Mercury Edit 2 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Trinity Large Thinking accepts text; Ornith 1.5 122B accepts text and images; Mercury Edit 2 accepts text. Ornith 1.5 122B handles the widest range of inputs.

Are any of these open source?

Trinity Large Thinking and Ornith 1.5 122B publishes its weights (OpenMDW-1.1 and MIT) and can be self-hosted; Mercury Edit 2 is proprietary.

Which is newer?

Ornith 1.5 122B is the newest, released Oct 20, 2026. Trinity Large Thinking came out Apr 1, 2026; Mercury Edit 2 came out Mar 30, 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.